© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60293
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an effort to reconnect or catch up with people or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollo
    -0.08
    ongan
    -0.07
    ngth
    -0.07
    ackers
    -0.07
    ashed
    -0.07
    ÙĦاÙĦ
    -0.07
    kem
    -0.07
    awa
    -0.06
    NotFoundError
    -0.06
    umo
    -0.06
    POSITIVE LOGITS
     with
    0.07
     catch
    0.07
    ingly
    0.07
    ogue
    0.07
    icut
    0.06
     catches
    0.06
    pus
    0.06
     stre
    0.06
    917
    0.06
     catching
    0.06
    Activations Density 0.004%

    No Known Activations